Dr Kerry Hempenstall, Senior Industry Fellow, School of Education, RMIT University, Melbourne, Australia.
All my blogs can be viewed on-line or downloaded as a Word file or PDF at https://www.dropbox.com/sh/olxpifutwcgvg8j/AABU8YNr4ZxiXPXzvHrrirR8a?dl=0
This study examines the effects of an explicit phonics-emphasis Direct Instruction beginning reading program on the phonological processes of students with teacher-identified serious reading problems attending a northern Melbourne reading intervention centre. The students (16 males and 10 females, mean age 8.8 years) were assigned to the treatment condition or to a wait-list comparison group. The 13 students in the intervention group received 100 lessons (in 2 groups) of the Teach Your Child to Read in 100 Easy Lessons program from a teacher at the reading intervention centre.
When compared with a similar cohort of wait-list students, the students made statistically significant and educationally large gains in the phonologically-related processes of word attack, phonemic awareness, phonological recoding in lexical access, phonological recoding in working memory and spelling. The study contributes to the long-standing debate on how best to ensure that children learn to read; to the understanding of the relationship between phonological processes and reading; to an understanding of the effects of the current instructional approach to reading on at-risk children; and, how additional or alternative approaches more attuned to the findings of reading research may improve the effectiveness of the educational system.
Education has a history of regularly adopting new ideas, but it has done so without the wide-scale assessment and scientific research that is necessary to distinguish effective from ineffective reforms. This absence of a scientific perspective has precluded systematic improvement in the education system, and it has impeded growth in the teaching profession for a long time (Carnine, 1995; Hempenstall, 1996; Marshall, 1993; Stone, 1996).
Over the past dozen years, there has been a marked acceptance of employing an evidence basis for teaching practice. This has been particularly noticeable in the USA and England, though only recently, in Australia. It is a change that is evident in fields other than education, for example, the rise of Evidence-Based Medicine in patient care (Sackett, Rosenberg, Gray, Haynes, & Richardson, 1996), and Empirically Validated Treatment in psychotherapy (American Psychological Association, 1996).
This has been driven partly by governments wanting to ensure that the costs associated with education are well spent. However, governments too are beginning to adopt evidence-based practice in their own domains. Most notably:
Since taking office, the President has emphasized the need to use evidence and rigorous evaluation in budget, management, and policy decisions to make government work effectively. This need has only grown in the current fiscal environment. Where evidence is strong, we should act on it. Where evidence is suggestive, we should consider it. Where evidence is weak, we should build the knowledge to support better decisions in the future (Zient, 2012).
Another factor driving this move relates to the similarity in recommendations between numerous national and state reports. In the USA, for example, the National Institute for Child Health and Human Development (Lyon, 1998), the National Reading Panel (National Reading Panel, 2000), the National Institute of the American Institutes for Research (1999), the National Research Council (Snow, Burns & Griffin, 1998), the Texas Reading Initiative (1996), and the National Early Literacy Panel (National Early Literacy Panel, 2009) highlighted the considerable consensus existing about the crucial elements of reading development and instruction. The importance of phonemic awareness and systematic synthetic phonics instruction is clearly explicated in these reports that relied heavily on empirical evidence for their findings.
In England, the National Literacy Strategy (Department of Education and Employment, 1998) was released to all primary schools, requiring them to abandon the current Whole Language approach to reading. Components of the former system, such as teaching students to rely on context clues to aid word reading, were discredited in the Strategy, and explicit phonics instruction was mandated from the earliest stages of reading instruction. “There must be systematic, regular, and frequent teaching of phonological awareness, phonics and spelling.” p.11 (Department for Education and Employment, 1998). This apparently firm position made little impact on what occurred in classrooms, and England went through the process again. This time the Rose Report (2006) was more forthright about implementing evidence-based approaches to instruction, and despite much opposition a Primary National Strategy (2006) was introduced - with substantially more impact.
The development of criteria for acceptable research evidence is a common element in the re-weighting of empirical research in the professional fields mentioned above. In the case of reading, it has made easier the task of convincing the educational community how valuable in informing practice can be the findings of rigorous research. Having established these criteria, it becomes easier to determine which of the plethora of reading programs available do have adequate research support at any given time.
The examination of existing evidence employing stringent criteria by a range of groups has supported Direct Instruction as a valuable approach to reading instruction for both regular and struggling readers. The Direct Instruction model has a relatively long history in reading education, the first program having been published in 1969. However, there has been surprisingly little serious attention paid to it from both the education and wider educational research communities, despite its strong body of supportive empirical evidence. Reports of Operation Follow Through (Engelmann, Becker, Carnine, & Gersten, 1988; Grossen, 1996), and the studies reported in meta-analyses by the American Institute for Research (2006), Borman (2007), Hattie (2009), White (1988) and by Adams and Engelmann (1996) have not been accorded the attention that might have been expected. Other studies and reports have also been supportive of Direct Instruction: For example, the American Federation of Teachers series of documents Building From The Best, Learning From What Works names Direct Instruction programs among each of its recommendations across different facets of education: Seven Promising Reading and English Language Arts Programs, Three Promising High School Remedial Reading Programs, Five Promising Remedial Reading Intervention Program, and Six Promising Schoolwide Reform Programs.
A report from the American Institutes for Research (1999), An Educators' Guide to School-wide Reform, found that only three programs, Direct Instruction among them, had adequate evidence of effectiveness in reading instruction. Another report, Reading Programs that Work: A Review of Programs for Pre-Kindergarten to 4th Grade (Schacter, 1999), similarly includes Direct Instruction among six school-wide effective reading models. A comprehensive bibliography of Direct Instruction studies can be found at the Association for Direct Instruction website (ADI, 2013).
These reports have been influential in drawing attention to the large corpus of supportive research developed over the years indicative of the effectiveness of the Direct Instruction model across a wide range of educational settings. The model is being implemented with varying degrees of fidelity in increasing numbers of school settings. In the USA, this interest was furthered by the impact of the Reading Excellence Act (The 1999 Omnibus Appropriations Bill, 1998) and the Elimination of Reading Deficit Act (Committee on Education and the Workforce, 2000) with their emphasis on empirically supported programs as a requirement for federal funding. As a consequence, there was been a very rapid rise in interest within the educational community. As an indication, the number of educational web pages that now make reference to Direct Instruction has increased dramatically in the past 10 years, as the use of an Internet search engine will attest.
Considering the two aspects of reading research described above: that is, the theoretical and the empirical, it is evident that the Direct Instruction model has strengths in each area to support its use. In line with current research findings, the programs focus on critical areas such as phonemic awareness (the ability to decompose the spoken word into its constituent sounds, and the ability to blend sounds) and letter-sound relationships. The areas critical for struggling students are paid careful attention in the program design. These are adequate lesson frequency (daily) and sufficient daily and spaced practice to reduce the risk of forgetting, immediate correction of errors to guide the student towards mastery, and continuous assessment of progress to validate the effectiveness of the teaching. Refreshingly, the assessment emphasises the teaching process rather than the child as the major issue. Failure to learn is viewed as failure to teach effectively, and specific teaching procedures are developed to redress the problems should lack of progress be observed. The emphasis on teaching quality rather than learner quality makes redundant any explanations of failure based on intelligence, race, readiness, first language, or home background. It is an empowering approach because it acknowledges and reinforces the status and power of teachers to make a real difference to students.
Over the past 15 years in Victoria, Australia there was a parallel rise in the adoption of Direct Instruction programs without any state or federal government support. There are at least 360 schools in Victoria that have implemented Direct Instruction programs (McGraw Hill, personal communication, February 2000), and teacher interest-groups are forming. There have been numerous recent federal and state government statements about appropriate teaching models, and the former wholesale acceptance of the Whole Language model is sharply declining, except for the maintenance of its near-relation Reading Recovery as the first line of remediation. It is an expensive intervention, given that while it was expected to be used with about 20% of first grade students (Public Accounts and Estimates Committee, 1999), in fact the use has been for between 40% and 50% of first grade students (Auditor-General, 2009). Further, the Auditor-General criticised the education department for its lack of any evaluation of the success or otherwise of this expensive intervention.
It is interesting then, that despite the absence of an Australian federal mandate (as in the USA and Great Britain), there is an apparent gradual shift towards research-supported programs and approaches. How this circumstance may have arisen is open to conjecture, but some possible influences are described below.
In recent years, Australian federal and state governments have introduced large scale testing programs (such as the federal NAPLAN), and have participated in international comparison studies, such as 2011 PIRLS (Progress in International Reading Literacy Study) and 2009 PISA (Programme for International Student Assessment). Community interest in the generally disappointing and controversial findings has prompted schools to address this hitherto hidden problem. Twenty years ago the Report of the House of Representatives Standing Committee on Employment, Education and Training "The Literacy Challenge" (Australian Government House of Representatives Enquiry, 1993), estimated that up to 20% of children complete primary school with residual literacy problems. In the past few years it has become evident that the situation is now more severe (Australian Government Productivity Commission, 2011; Nous Group Consortium, 2011), despite huge sums being invested in education. Unfortunately, much has been spent in class size reduction, despite the lack of evidence that this is a major determinant of student outcome (Leigh & Ryan, 2008). The 2011 PIRLS results indicate that 24% of year four students did not meet the study’s “intermediate benchmark,” which is regarded as the minimal acceptable standard of literacy. The 2009 PISA results revealed that reading literacy of Australian 15-year-old students had fallen sharply over the past decade.
There has been wide reporting in the mass media, causing many questions to be asked about the quality of teaching children receive, and about the quality of training received by teachers. The federal government has responded with a national curriculum, a focus on evidence-based teaching practice, and the promise of a shaking up of teacher education and entry requirements.
Schools wish to be seen to be doing something positive, and the rise in consumerism among parents in Australia has hastened that process. Parents have the right to choose a school for their children, and schools do not wish to be outbid by those offering more assistance to students who struggle. The Direct Instruction model has some administrative features that make it an attractive option. Lessons fit readily into a school timetable, their completeness relieves schools from developing their own curricula, and the clearly defined skill objectives make reporting to parents a simple task. As the number of participating schools increases, it is becoming easier for a school contemplating the implementation of one or more programs to view those programs in operation at a school nearby.
Many of the schools employing Direct Instruction programs have opted for the remedial decoding program known as Corrective Reading: Decoding (Engelmann, Hanner, & Johnson, 1999) for mid-primary and older struggling readers, as it is around that time that the developmental lag explanation, often provided by schools to parents, begins to ring hollow. In addition, it is recognised that the earlier reading problems are addressed, the greater the likelihood of satisfactory and speedy resolution. In fact, Alexander, Entwisle, and Olsen (1997) claim that reading achievement occurs twice as fast in first as it does in third grade, whilst Hall and Moats (1999) reported a National Institute of Child Health and Human Development finding that it takes four times as much assistance to improve a child’s reading skills if help is delayed until Year Four than if it is begun in the Prep year.
Many of these older children have experienced the debilitating sequence of interacting skill deficits described by Stanovich (1986) as the Matthew Effect. For example, an early lack of phonemic awareness leads to a failure to master the alphabetic principle. This further entails slow, error-prone decoding, the overuse of contextual cues, and poor comprehension. This resultant laborious, unsatisfying reading style leads students to avoid text, with a consequential reduction in vocabulary growth, and a broadening of the skill deficit. The lack of practice means fewer words can be read by sight, thereby restricting automaticity. The continued expenditure of cognitive attention on decoding leaves few resources available for comprehension, and so the student’s difficulties are compounded. The longer this set of circumstances prevails, the further delayed the student becomes, the more pervasive becomes the problem, and the more difficult the rescue operation. Hence, the concern for intervening earlier in this escalating chain.
Such findings aroused interest in examining the effects of a Direct Instruction program specifically designed for beginning readers: Teach Your Child to Read in 100 Easy Lessons (Engelmann, Haddox, & Bruner, 1983). If the intervention is commenced earlier, when the obvious primary deficit involves under-developed phonemic awareness (Lyon, 1999), and this deficit is targeted, it is reasonable to anticipate a more efficacious process. If increased phonemic awareness and an early understanding of the alphabetic principle are the outcomes (thus precluding the by-products of early reading failure), the intervention at this stage should be more effective, efficient, and socially just.
Although the content of the Teach Your Child to Read in 100 Easy Lessons (Engelmann et al., 1983) was developed earlier than most of the research into phonemic awareness, it is now becoming more evident that the combination of letter-sound instruction with phonemic awareness training (as evidenced in the 100 Lessons program) is a potent one in stimulating early reading development (Byrne & Fielding-Barnsley, 1991, 1993, 1995; Ehri, 1987; Hatcher, Hulme, & Ellis, 1994; Perfetti, Beck, Bell, & Hughes, 1987; Schneider, Roth, & Ennemoser, 2000; Torgesen, Wagner, & Rashotte, 1994).
However, a wide range of phonemic awareness tasks have been incorporated into phonemic awareness programs, and a vital question (especially for at-risk students) is what combination of tasks is optimally related to accelerated reading development? This is particularly important for those who are at-risk, as (academically engaged) time is of the essence.
Torgesen, Morgan, and Davis (1992) tested two types of phonemic awareness training approaches - blending only, and a combination of blending and segmenting - and compared them to a language experience control group. The small groups trained three times per week for 20 minutes for a total of 7-8 weeks. The blending only group improved only on blending, their segmentation skills remaining similar to that of the controls. Similarly, their ability to learn in a reading analogue task did not significantly exceed that of the control group, indicating a lack of generalisation of this skill to this reading task. In contrast, the combination of blending and segmenting led to significant improvements in both skills, and evidence of transfer to the reading task. The authors acknowledge that the introduction of letter-sound training may have even further enhanced the transfer to reading tasks had they incorporated such strategy.
Davidson and Jenkins (1994) in a similar study included a segmentation-only training group, and while they noted some transfer to a reading analogue task for that group, they too argued against teaching only one type of phonemic awareness strategy, as generalisation of awareness is likely to be compromised.
O’Connor, Slocum, and Jenkins (1995) reported a study in which the combination of letter-sounds, blending and segmenting instruction led to educationally significant gains for at-risk beginning readers. The program intervention lasted a total of five hours (15 minutes twice weekly for 10 weeks). A second experimental group had a much greater range of phonemic awareness activities (in addition to segmentation and blending) but showed no increase in reading development over the first experimental group. The authors argue that both experimental groups were able to generalise the phonemic awareness skills they were taught, that is, they attained phonological insight, and were able to relate it to the reading process. Importantly, their findings suggest that the combination of blending and segmenting is sufficient to create this condition.
Lovett et al. (1994) used a 35 lesson training program developed from Reading Mastery: Fast Cycle 1 & 2 (Engelmann, & Bruner, 1984), and Corrective Reading to teach word identification to dyslexic students for one hour four times per week. They compared results to a control group taught a study skills program, and achieved highly significant post-test gains for the experimental group - effect sizes (d) of 0.76, 1.11, and 0.90 on the three training measures. The transfer to real words was impressive, and "was based on the successful training of what is considered the core deficit of developmental dyslexia: phonological processing and nonword reading skill" (p. 818). Further, they argue, "this training success rests on embedding letter-sound training in an intensive phonological training program" (p. 819). In a further study, offering 70 hours of DI based phonological instruction Lovett et al. (2000) noted similarly large treatment effects, evident even in comprehension tasks.
Thus, there is evidence to support the use of a program that explicitly teaches letter-sound correspondence, and which simultaneously links this knowledge to two critical phonemic awareness skills, blending and segmenting. This should not surprise since segmenting and blending are the phonemic awareness processes most closely involved in reading, and letter-sound knowledge is both a prompt, and a necessary condition for this phonemic awareness knowledge to be useful in reading. The 100 Lessons program meets these dual requirements of theoretically and empirically validated practice. Additionally, it had been successfully used in the RMIT Psychology Clinic for many years. In that setting however, it was parents who were trained to present the program individually to their own child.
Another potential benefit of this program is to provide an additional option to schools that are currently expending a great deal of resources on the Reading Recovery program (Clay, 1979, 1985).
Read the rest of this article at https://www.dropbox.com/sh/olxpifutwcgvg8j/AABU8YNr4ZxiXPXzvHrrirR8a?dl=0
